FeinNote — Audio Transcription & Subtitles

    1

    Transcribe audio with verifiable source preservation, optional refinement, and timestamp-backed subtitle exports.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    FeinNote — Audio Transcription & Subtitles

    Example session with this skill installed

    Transcribe interview_01.mp3 using ElevenLabs. Save the original transcript and then generate a refined version. Export the final results to the current job directory.

    • Read your context and instructions
    • Compiled the feinnote

    I have initiated the transcription for interview_01.mp3. The audio was processed via ElevenLabs Speech to Text. The raw transcript was captured and saved before applying refinement.

    Job Status: fein-note-8821

    IDSource LabelStatusFiles Generated
    1interview_01.mp3Completedoriginal_01.txt, refined_01.txt

    Transcription Details

    • Tool: ElevenLabs Speech to Text
    • Language: English (Detected)
    • Duration: 04:12
    • Refinement: Applied via refine.md logic
    • Output Directory: /authorized/jobs/8821/

    The original recognized text has been preserved as a UTF-8 TXT file. The refined version addresses minor disfluencies while maintaining the core speaker intent. No subtitle offsets were requested for this specific TXT export.

    Next steps

    1. Review refined_01.txt for any industry-specific terminology accuracy.
    2. Run the export script if you require SRT or VTT subtitle formats for this recording.
    3. Clean up the transient audio staging files once you have verified the transcript downloads.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    FeinNote is a lightweight AI agent skill for audio transcription, transcript refinement, and subtitle export.

    It helps your AI agent organize the complete workflow, from receiving audio files to delivering readable transcripts and timestamped subtitles.

    Features

    • Audio transcription: Use an available local speech recognition tool or an authorized cloud STT provider.
    • Batch processing: Process multiple recordings separately and preserve their results.
    • Original transcripts: Keep the original recognized text unchanged.
    • Optional AI refinement: Improve punctuation, paragraphs, and dialogue formatting while preserving the original version.
    • Subtitle export: Generate SRT and VTT subtitles using genuine timestamps from the speech recognition tool.
    • Text export: Save transcripts as UTF-8 TXT files.
    • Error handling: Report unsupported files, missing timestamps, and processing failures without discarding successful results.
    • Privacy controls: Request permission before sending audio or text to external services or making paid API calls.

    Requirements

    The receiving AI agent must have access to a compatible speech-to-text tool. The bundled exporter requires Python 3.10+ and a writable workspace.

    FeinNote Skill does not include Whisper models or a built-in speech recognition engine. Cloud transcription may incur additional provider charges.

    The complete workflow through Agensi MCP has not yet been independently verified.

    Open-source origins

    Inspired by the open-source FeinNote Windows desktop application.

    Source project: https://github.com/LokiSkardina/FeinNote

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires Python 3.10+ for SRT/VTT exports. Subtitle generation is restricted to original recognized text. No automatic software installation.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listedtoday

    What's inside

    Frequently Asked Questions

    Unlike standard prompts that might hallucinate or lose timing data, this skill captures raw STT output first, creating a 'source of truth' before any optional refinement occurs to ensure 100% auditability.

    The skill is built for the Agensi MCP framework and requires Python 3.10+; it works with both remote providers like ElevenLabs and local STT engines for users requiring air-gapped workflows.

    Yes, the skill includes specialized export utilities that use original source timestamps to generate accurately synchronized SRT and VTT files for video production.

    You receive the complete Python-based transcription pipeline, including the normalization scripts, verification mapping tools, and subtitle export utilities.

    The skill uses a verification mapping system that assigns numeric IDs to every recording, allowing you to track the status and input order of multiple files simultaneously.

    The refinement layer is optional and strictly separated; you can choose to keep the raw transcript as-is or apply post-processing for better readability without losing the original timestamps.

    New in Agents & Orchestration

    Free